基于贝叶斯网络的复杂系统故障诊断

摘要/Abstract

摘要： 系统结构和部件关系复杂、试验费用昂贵是小样本下基于不确定性信息的决策问题。针对其特点，建立了基于贝叶斯网络的复杂系统故障诊断模型，并提出采用Leaky Noisy-OR模型来降低数据需求量和计算复杂度。经研究表明，这种方法能综合利用各种来源信息，具有知识表达明确、样本需求量小、故障诊断准确度高等特点，可为复杂系统故障诊断提供决策支持。

关键词: 复杂系统, 故障诊断, 贝叶斯网络

Abstract: The structure and relationship of components are complicated in complex system, and the test-cost of complex system is high. So, the fault diagnosis of complex system is the decision with uncertainty under small sample. A Bayesian networks (BN) model for fault diagnosis of complex system is built up，furthermore, the Leaky Noisy-OR model is used to reduce the requirements for data and computation complexity. The study shows that the method for fault diagnosis of complex system can utilize all kinds of information, represent knowledge definitely, demand small sample and diagnose the faults accurately. The method can guide the decision for fault diagnosis of complex system.

Key words: complex system, fault diagnosis, Bayesian networks, information fusion

中图分类号:

TB4
TP18

王华伟，周经伦，何祖玉，沙基昌. 基于贝叶斯网络的复杂系统故障诊断[J]. .

WANG Hua-wei，ZHOU Jing-lun，HE Zu-yu，SHA Ji-chang. Fault Diagnosis of Complex System Based on Bayesian Networks[J]. .

参考文献

［1］XU Zhangsui, FANG Liqing, WANG Xiwu, ZUO Xianzhang. Diagnosis principle and application for the fault Information[M]. Beijing: National Defence Industry Press,2000(in Chinese).[徐章遂，方立清，王希武，左宪章.故障信息诊断原理及应用[M].北京:国防工业出版社, 2000.]

[2]WU Jinpei.Intelligent fault diagnosis and neural networks［M］. Beijing: Science Press,1997(in Chinese).[吴今培.智能故障诊断与神经网络［M］.北京：科学出版社,1997.]

[3]PORTINALE L. Behavioral petri-nets:a model for diagnostic knowledge representing and reasoning[J]. IEEE Transactions on System, Man and Cybernetics—Part B:Cybernetics, 1997, 27(2):184-195.

[4]Inien SYU, LANG S D. Adapting a diagnostic problem-solving model to information retrieval[J]. Information Processing and Management，2000,36:313-330.

[5]FU Jun，HE Wei，ZHANG Hongcai，et al. A study of fault diagnosis based on bayesian networks[J]. Journal of Shanghai Maritime University, 2001,22 (3):68-71, 77.

[6]BREESE J S，HECKERMAN D. Decision-theoretic case-based reasoning[J]. IEEE Transactions on Systems, Man and Cybernetics-Part A: Systems and Humans, 1996,26 (6):838-842.

[7]RAKAR A, JURICIC D, BALL P. Transferable belief model in fault diagnosis [J]. Engineering Applications of Artificial Intellignece, 1999, 12: 555-567.

[8]HAHLL G. Combing disparate sources of information in the safety assessment of software-based system［J］. Nuclear Engine and Design, 2000, 195:307-319.

[9]MUSSI S. Diagnostic expert systems: a method for engineering knowledge used in sequential diagnosis［J］. Expert Systems, 2000, 17(4): 199-211.

[10]PEARL J. Probabilistic reasoning in intelligent systems:networks of plausible inference[M]. San Mateo, CA: Morgan Kaufmann,1988.

[11]NEAPOLITAN R E.Probabilistic reasoning in expert systems[M]. New York:Wiley, 1990.

[12]ONISKO′ A, DRUZDZEL M J，WAYSYLUK H. Learning bayesian network parameters from data sets: application of Noisy-OR Gates[J]. International Journal of Approximation Reasoning，2001,27:165-182.

[13]ZHANG Yulin, WU Jianjun. Liquid rocket engine health monitoring technology[M]. Changsha: National University of Defense Technology Press,1998(in Chinese). [张育林，吴建军.液体火箭发动机健康监控技术［M］.长沙：国防科技大学出版社,1998.]

[1]	付松,钟诗胜,林琳,张永健. 基于迁移学习的民航发动机小样本故障诊断[J]. 计算机集成制造系统, 2021, 27(12): 3450-3461.
[2]	王欢,张春,张宁,陈耀华. 具有强泛化性的高铁逆变器开路故障诊断算法[J]. 计算机集成制造系统, 2021, 27(11): 3236-3246.
[3]	徐彦伟,蔡薇薇,颉潭成,陈立海,刘明明. 变工况下基于信息融合的地铁牵引电机轴承故障智能诊断[J]. 计算机集成制造系统, 2021, 27(11): 3247-3258.
[4]	孙晨,文龙,李新宇,高亮,丛建臣. 基于自动机器学习的不平衡故障诊断方法[J]. 计算机集成制造系统, 2021, 27(10): 2837-2847.
[5]	耿苏杰,王秀利. 基于模糊贝叶斯网络的电力设备故障诊断和状态评估[J]. 计算机集成制造系统, 2021, 27(1): 64-72.
[6]	刘鹏程,孙林夫,张常有,王波. 基于交互注意力机制网络模型的故障文本分类[J]. 计算机集成制造系统, 2021, 27(1): 73-90.
[7]	彭成,贺婧,唐朝晖,陈青,桂卫华. 基于双维度EKNN的滚动轴承早期故障分类算法[J]. 计算机集成制造系统, 2021, 27(1): 91-102.
[8]	张文龙,胡天亮,王艳洁,魏永利. 云/边缘协同的轴承故障诊断方法[J]. 计算机集成制造系统, 2020, 26(第3): 589-599.
[9]	刘华一,鄢萍,周强,辛洋,张自凯,潘吉财. 基于语义网的机床故障诊断知识扩展方法[J]. 计算机集成制造系统, 2020, 26(第3): 609-622.
[10]	张卫贞1,曾建潮2,石慧1,董增寿1. 基于核密度估计的实时剩余寿命预测[J]. 计算机集成制造系统, 2020, 26(7): 1794-1801.
[11]	辜振谱,刘晓波,韩子东,洪连环. 基于改进密度峰值聚类的航空发动机故障诊断[J]. 计算机集成制造系统, 2020, 26(5期): 1211-1217.
[12]	马超民,赵丹华,辛灏. 基于用户体验的智能装备人机交互界面设计[J]. 计算机集成制造系统, 2020, 26(10): 2650-2660.
[13]	张珊珊,李方义,贾秀杰,周丽蓉,刘浩华,张传伟,孔琳. 面向变速箱磨损状态评估的灰靶模型优化[J]. 计算机集成制造系统, 2019, 25(第9): 2159-2166.
[14]	赵宏宇,沈江,安邦. 基于代价敏感方法的智能制造故障诊断[J]. 计算机集成制造系统, 2019, 25(第9): 2180-2187.
[15]	宋亚,夏唐斌,郑宇,卓鹏程,潘尔顺. 基于Autoencoder-BLSTM的涡扇发动机剩余寿命预测[J]. 计算机集成制造系统, 2019, 25(第7): 1611-1619.